CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

ainativedev/aidevcon-2026-nyc

AI Native DevCon 2026 New York — practical agent skills grounded in conference talks

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

outline.mdskills/talk-pari-patel-agent-awareness/references/

Source outline

Read transcript.md for evidence. Promotion cues 227–237 are omitted.

TimeCuesTopic
00:00–02:211–36Company introduction and overloaded-user anecdote
02:25–03:1737–49Memory versus awareness
03:26–05:1552–80Depth, pacing and handoff failures
05:19–06:5981–105User-model gap and narrow definition
07:03–09:54106–152Preferences, task context, feedback and behavior dials
09:58–12:55153–198Four-field state and reported coach implementation
12:59–14:37199–226Context-rich decision handoff
15:21–16:40238–258Cooldowns, batching and user-set interruption budget
16:45–18:15259–279Interaction evaluation signals
18:15–20:48280–318Neural-sensing claims and unshipped coding proposal
20:53–23:28319–358Opt-in, visibility, privacy and takeaways
23:28–29:17359–444Q&A on adaptation, audio and reduced-state inputs

Short quotations

  • “the state actually belongs to the user and not the agent.” — excerpt, cue 187, 12:14.
  • “We have not shipped this into a coding agent.” — excerpt, cue 301, 19:45.
  • “everything is of course opt in.” — excerpt, cue 321, 21:00.

Limits

The roughly 85% validation claim lacks metric, sample and study design details in this source. Neural coding-agent integration is proposed, despite reported use of an adaptation workflow in the company's coach. Audio correlation is not yet implemented. Behavioral signals do not prove fatigue, stress, intelligence or consent. No empirical uplift from the proposed coding-agent loop is supplied.

skills

talk-pari-patel-agent-awareness

tile.json